05-04-2012, 02:36 PM
AUTOMATED SPEECH RECOGNITION APPROACH TO CONTINUOUS
CUE-SYMBOLS GENERATION
[attachment=19557]
INTRODUCTION
Humans know each other by conveying their ideas,
thoughts, and experiences to the people around them.
There are numerous ways to achieve this and the best
one among all is the gift of “Speech”. Through speech
everyone can very convincingly transfer their thoughts
and understand each other. It will be injustice if we
ignore those who are deprived of this invaluable gift.
The only means of communication available to the
vocally disabled is the use of “Sign Language”.
SURVEY
Various systems were proposed for the automatic
recognition of sign language Don Pearson in his
approach “Visual Communication Systems for the
Deaf” [1] presented a two way communication
approach, where he proposed the practicality of
switched television for both deaf-to-hearing and deafto-
deaf communication. In his approach, attention is
given to the requirements of picture communication
systems, which enable the deaf to communicate over
distances using telephone lines. This section discusses
some research done on translating other text and spoken
languages to Sign language.
SYSTEM APPROACH
An automated speech recognition system is
proposed for the recognition of speech signal and
transforms it to a cue symbol recognizable by vocally
disabled people. Figure 1 shows the proposed
architecture for automated recognition system.
WORKING PRINCIPLE
The proposed system perform three principle
functions
1) Capture and parameterization of the acoustic
speech input.
2) Signal identification via speech recognition and
generates an equivalent symbol.
HIDDEN MARKOW MODEL OPERATION
(HMM)
The project implements a speech recognition
system based on the speech reading and the cue
samples passed to the processing unit. The processing
system consists of a speech recognition unit with cue
reader, which determines the speech signal and
reproduces the extracted speech signal using HMM
process.
CONCLUSION
This paper presents an approach towards
automated recognition of speech signal for vocally
disabled people. The system proposed could efficiently
recognize the speech signal using HMM and generate
an equivalent cue symbol. The proposed AISR system
find its application for the vocally disable peoples for
providing a communication link between normal and
disabled people. The system could be integrated with
finger spelling recognition system such as “Boltay
Haath” for a complete communication between the
common person and the vocally disable people. For the
suggested work converting speech sample to characters
and then cue is to be further extended for generating
video samples of continuous sentences.
CUE-SYMBOLS GENERATION
[attachment=19557]
INTRODUCTION
Humans know each other by conveying their ideas,
thoughts, and experiences to the people around them.
There are numerous ways to achieve this and the best
one among all is the gift of “Speech”. Through speech
everyone can very convincingly transfer their thoughts
and understand each other. It will be injustice if we
ignore those who are deprived of this invaluable gift.
The only means of communication available to the
vocally disabled is the use of “Sign Language”.
SURVEY
Various systems were proposed for the automatic
recognition of sign language Don Pearson in his
approach “Visual Communication Systems for the
Deaf” [1] presented a two way communication
approach, where he proposed the practicality of
switched television for both deaf-to-hearing and deafto-
deaf communication. In his approach, attention is
given to the requirements of picture communication
systems, which enable the deaf to communicate over
distances using telephone lines. This section discusses
some research done on translating other text and spoken
languages to Sign language.
SYSTEM APPROACH
An automated speech recognition system is
proposed for the recognition of speech signal and
transforms it to a cue symbol recognizable by vocally
disabled people. Figure 1 shows the proposed
architecture for automated recognition system.
WORKING PRINCIPLE
The proposed system perform three principle
functions
1) Capture and parameterization of the acoustic
speech input.
2) Signal identification via speech recognition and
generates an equivalent symbol.
HIDDEN MARKOW MODEL OPERATION
(HMM)
The project implements a speech recognition
system based on the speech reading and the cue
samples passed to the processing unit. The processing
system consists of a speech recognition unit with cue
reader, which determines the speech signal and
reproduces the extracted speech signal using HMM
process.
CONCLUSION
This paper presents an approach towards
automated recognition of speech signal for vocally
disabled people. The system proposed could efficiently
recognize the speech signal using HMM and generate
an equivalent cue symbol. The proposed AISR system
find its application for the vocally disable peoples for
providing a communication link between normal and
disabled people. The system could be integrated with
finger spelling recognition system such as “Boltay
Haath” for a complete communication between the
common person and the vocally disable people. For the
suggested work converting speech sample to characters
and then cue is to be further extended for generating
video samples of continuous sentences.